3 from __future__
import unicode_literals
14 from .common
import InfoExtractor
, SearchInfoExtractor
15 from ..jsinterp
import JSInterpreter
16 from ..swfinterp
import SWFInterpreter
17 from ..compat
import (
22 compat_urllib_parse_unquote
,
23 compat_urllib_parse_unquote_plus
,
24 compat_urllib_parse_urlencode
,
25 compat_urllib_parse_urlparse
,
36 get_element_by_attribute
,
59 class YoutubeBaseInfoExtractor(InfoExtractor
):
60 """Provide base functions for Youtube extractors"""
61 _LOGIN_URL
= 'https://accounts.google.com/ServiceLogin'
62 _TWOFACTOR_URL
= 'https://accounts.google.com/signin/challenge'
64 _LOOKUP_URL
= 'https://accounts.google.com/_/signin/sl/lookup'
65 _CHALLENGE_URL
= 'https://accounts.google.com/_/signin/sl/challenge'
66 _TFA_URL
= 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
68 _NETRC_MACHINE
= 'youtube'
69 # If True it will raise an error if no login info is provided
70 _LOGIN_REQUIRED
= False
72 _PLAYLIST_ID_RE
= r
'(?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)[0-9A-Za-z-_]{10,}'
74 def _set_language(self
):
76 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
77 # YouTube sets the expire time to about two months
78 expire_time
=time
.time() + 2 * 30 * 24 * 3600)
80 def _ids_to_results(self
, ids
):
82 self
.url_result(vid_id
, 'Youtube', video_id
=vid_id
)
87 Attempt to log in to YouTube.
88 True is returned if successful or skipped.
89 False is returned if login failed.
91 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
93 username
, password
= self
._get
_login
_info
()
94 # No authentication to be performed
96 if self
._LOGIN
_REQUIRED
and self
._downloader
.params
.get('cookiefile') is None:
97 raise ExtractorError('No login info available, needed for using %s.' % self
.IE_NAME
, expected
=True)
100 login_page
= self
._download
_webpage
(
101 self
._LOGIN
_URL
, None,
102 note
='Downloading login page',
103 errnote
='unable to fetch login page', fatal
=False)
104 if login_page
is False:
107 login_form
= self
._hidden
_inputs
(login_page
)
109 def req(url
, f_req
, note
, errnote
):
110 data
= login_form
.copy()
113 'checkConnection': 'youtube',
114 'checkedDomains': 'youtube',
116 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
117 'f.req': json
.dumps(f_req
),
118 'flowName': 'GlifWebSignIn',
119 'flowEntry': 'ServiceLogin',
120 # TODO: reverse actual botguard identifier generation algo
121 'bgRequest': '["identifier",""]',
123 return self
._download
_json
(
124 url
, None, note
=note
, errnote
=errnote
,
125 transform_source
=lambda s
: re
.sub(r
'^[^[]*', '', s
),
127 data
=urlencode_postdata(data
), headers
={
128 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
129 'Google-Accounts-XSRF': 1,
133 self
._downloader
.report_warning(message
)
137 None, [], None, 'US', None, None, 2, False, True,
141 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn',
143 1, [None, None, []], None, None, None, True
148 lookup_results
= req(
149 self
._LOOKUP
_URL
, lookup_req
,
150 'Looking up account info', 'Unable to look up account info')
152 if lookup_results
is False:
155 user_hash
= try_get(lookup_results
, lambda x
: x
[0][2], compat_str
)
157 warn('Unable to extract user hash')
162 None, 1, None, [1, None, None, None, [password
, None, True]],
164 None, None, [2, 1, None, 1, 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn', None, [], 4],
165 1, [None, None, []], None, None, None, True
168 challenge_results
= req(
169 self
._CHALLENGE
_URL
, challenge_req
,
170 'Logging in', 'Unable to log in')
172 if challenge_results
is False:
175 login_res
= try_get(challenge_results
, lambda x
: x
[0][5], list)
177 login_msg
= try_get(login_res
, lambda x
: x
[5], compat_str
)
179 'Unable to login: %s' % 'Invalid password'
180 if login_msg
== 'INCORRECT_ANSWER_ENTERED' else login_msg
)
183 res
= try_get(challenge_results
, lambda x
: x
[0][-1], list)
185 warn('Unable to extract result entry')
188 login_challenge
= try_get(res
, lambda x
: x
[0][0], list)
190 challenge_str
= try_get(login_challenge
, lambda x
: x
[2], compat_str
)
191 if challenge_str
== 'TWO_STEP_VERIFICATION':
192 # SEND_SUCCESS - TFA code has been successfully sent to phone
193 # QUOTA_EXCEEDED - reached the limit of TFA codes
194 status
= try_get(login_challenge
, lambda x
: x
[5], compat_str
)
195 if status
== 'QUOTA_EXCEEDED':
196 warn('Exceeded the limit of TFA codes, try later')
199 tl
= try_get(challenge_results
, lambda x
: x
[1][2], compat_str
)
201 warn('Unable to extract TL')
204 tfa_code
= self
._get
_tfa
_info
('2-step verification code')
208 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
209 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
212 tfa_code
= remove_start(tfa_code
, 'G-')
215 user_hash
, None, 2, None,
217 9, None, None, None, None, None, None, None,
218 [None, tfa_code
, True, 2]
222 self
._TFA
_URL
.format(tl
), tfa_req
,
223 'Submitting TFA code', 'Unable to submit TFA code')
225 if tfa_results
is False:
228 tfa_res
= try_get(tfa_results
, lambda x
: x
[0][5], list)
230 tfa_msg
= try_get(tfa_res
, lambda x
: x
[5], compat_str
)
232 'Unable to finish TFA: %s' % 'Invalid TFA code'
233 if tfa_msg
== 'INCORRECT_ANSWER_ENTERED' else tfa_msg
)
236 check_cookie_url
= try_get(
237 tfa_results
, lambda x
: x
[0][-1][2], compat_str
)
240 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
241 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
242 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
244 challenge
= CHALLENGES
.get(
246 '%s returned error %s.' % (self
.IE_NAME
, challenge_str
))
247 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge
)
250 check_cookie_url
= try_get(res
, lambda x
: x
[2], compat_str
)
252 if not check_cookie_url
:
253 warn('Unable to extract CheckCookie URL')
256 check_cookie_results
= self
._download
_webpage
(
257 check_cookie_url
, None, 'Checking cookie', fatal
=False)
259 if check_cookie_results
is False:
262 if 'https://myaccount.google.com/' not in check_cookie_results
:
263 warn('Unable to log in')
268 def _download_webpage_handle(self
, *args
, **kwargs
):
269 query
= kwargs
.get('query', {}).copy()
270 query
['disable_polymer'] = 'true'
271 kwargs
['query'] = query
272 return super(YoutubeBaseInfoExtractor
, self
)._download
_webpage
_handle
(
273 *args
, **compat_kwargs(kwargs
))
275 def _real_initialize(self
):
276 if self
._downloader
is None:
279 if not self
._login
():
283 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor
):
284 # Extract entries from page with "Load more" button
285 def _entries(self
, page
, playlist_id
):
286 more_widget_html
= content_html
= page
287 for page_num
in itertools
.count(1):
288 for entry
in self
._process
_page
(content_html
):
291 mobj
= re
.search(r
'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html
)
297 while count
<= retries
:
299 # Downloading page may result in intermittent 5xx HTTP error
300 # that is usually worked around with a retry
301 more
= self
._download
_json
(
302 'https://youtube.com/%s' % mobj
.group('more'), playlist_id
,
303 'Downloading page #%s%s'
304 % (page_num
, ' (retry #%d)' % count
if count
else ''),
305 transform_source
=uppercase_escape
)
307 except ExtractorError
as e
:
308 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
in (500, 503):
314 content_html
= more
['content_html']
315 if not content_html
.strip():
316 # Some webpages show a "Load more" button but they don't
319 more_widget_html
= more
['load_more_widget_html']
322 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor
):
323 def _process_page(self
, content
):
324 for video_id
, video_title
in self
.extract_videos_from_page(content
):
325 yield self
.url_result(video_id
, 'Youtube', video_id
, video_title
)
327 def extract_videos_from_page(self
, page
):
330 for mobj
in re
.finditer(self
._VIDEO
_RE
, page
):
331 # The link with index 0 is not the first video of the playlist (not sure if still actual)
332 if 'index' in mobj
.groupdict() and mobj
.group('id') == '0':
334 video_id
= mobj
.group('id')
335 video_title
= unescapeHTML(mobj
.group('title'))
337 video_title
= video_title
.strip()
339 idx
= ids_in_page
.index(video_id
)
340 if video_title
and not titles_in_page
[idx
]:
341 titles_in_page
[idx
] = video_title
343 ids_in_page
.append(video_id
)
344 titles_in_page
.append(video_title
)
345 return zip(ids_in_page
, titles_in_page
)
348 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor
):
349 def _process_page(self
, content
):
350 for playlist_id
in orderedSet(re
.findall(
351 r
'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
353 yield self
.url_result(
354 'https://www.youtube.com/playlist?list=%s' % playlist_id
, 'YoutubePlaylist')
356 def _real_extract(self
, url
):
357 playlist_id
= self
._match
_id
(url
)
358 webpage
= self
._download
_webpage
(url
, playlist_id
)
359 title
= self
._og
_search
_title
(webpage
, fatal
=False)
360 return self
.playlist_result(self
._entries
(webpage
, playlist_id
), playlist_id
, title
)
363 class YoutubeIE(YoutubeBaseInfoExtractor
):
364 IE_DESC
= 'YouTube.com'
365 _VALID_URL
= r
"""(?x)^
367 (?:https?://|//) # http(s):// or protocol-independent URL
368 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
369 (?:www\.)?deturl\.com/www\.youtube\.com/|
370 (?:www\.)?pwnyoutube\.com/|
371 (?:www\.)?hooktube\.com/|
372 (?:www\.)?yourepeat\.com/|
373 tube\.majestyc\.net/|
374 # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
375 (?:(?:www|dev)\.)?invidio\.us/|
376 (?:(?:www|no)\.)?invidiou\.sh/|
377 (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/|
378 (?:www\.)?invidious\.kabi\.tk/|
379 (?:www\.)?invidious\.enkirton\.net/|
380 (?:www\.)?invidious\.13ad\.de/|
381 (?:www\.)?invidious\.mastodon\.host/|
382 (?:www\.)?tube\.poal\.co/|
383 (?:www\.)?vid\.wxzm\.sx/|
384 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
385 (?:.*?\#/)? # handle anchor (#/) redirect urls
386 (?: # the various things that can precede the ID:
387 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
388 |(?: # or the v= param in all its forms
389 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
390 (?:\?|\#!?) # the params delimiter ? or # or #!
391 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
396 youtu\.be| # just youtu.be/xxxx
397 vid\.plus| # or vid.plus/xxxx
398 zwearz\.com/watch| # or zwearz.com/watch/xxxx
400 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
402 )? # all until now is optional -> you can pass the naked ID
403 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
406 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
407 WL # WL are handled by the watch later IE
410 (?(1).+)? # if we found the ID, everything can follow
411 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
412 _NEXT_URL_RE
= r
'[\?&]next_url=([^&]+)'
414 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
415 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
416 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
417 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
418 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
419 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
420 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
421 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
422 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
423 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
424 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
425 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
426 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
427 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
428 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
429 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
430 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
431 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
435 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
436 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
437 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
438 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
439 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
440 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
441 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
443 # Apple HTTP Live Streaming
444 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
445 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
446 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
447 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
448 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
449 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
450 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
451 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
454 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
455 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
456 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
457 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
458 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
459 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}
, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
460 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
461 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
462 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
463 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
464 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
465 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
468 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}
,
469 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}
,
470 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}
,
471 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
472 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
473 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}
,
474 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}
,
477 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
478 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
479 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
480 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
481 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
482 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
483 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}
,
484 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
485 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
486 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
487 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
488 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
489 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
490 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
491 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
492 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
493 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
494 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
495 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
496 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
497 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
498 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
501 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}
,
502 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}
,
504 # Dash webm audio with opus inside
505 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}
,
506 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}
,
507 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}
,
510 '_rtmp': {'protocol': 'rtmp'}
,
512 # av01 video only formats sometimes served with "unknown" codecs
513 '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
514 '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
515 '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
516 '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
518 _SUBTITLE_FORMATS
= ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
525 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
529 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
530 'uploader': 'Philipp Hagemeister',
531 'uploader_id': 'phihag',
532 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
533 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
534 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
535 'upload_date': '20121002',
536 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
537 'categories': ['Science & Technology'],
538 'tags': ['youtube-dl'],
542 'dislike_count': int,
548 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
549 'note': 'Test generic use_cipher_signature video (#897)',
553 'upload_date': '20120506',
554 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
555 'alt_title': 'I Love It (feat. Charli XCX)',
556 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
557 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
558 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
559 'iconic ep', 'iconic', 'love', 'it'],
561 'uploader': 'Icona Pop',
562 'uploader_id': 'IconaPop',
563 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IconaPop',
564 'creator': 'Icona Pop',
565 'track': 'I Love It (feat. Charli XCX)',
566 'artist': 'Icona Pop',
570 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
571 'note': 'Test VEVO video with age protection (#956)',
575 'upload_date': '20130703',
576 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)',
577 'alt_title': 'Tunnel Vision',
578 'description': 'md5:07dab3356cde4199048e4c7cd93471e1',
580 'uploader': 'justintimberlakeVEVO',
581 'uploader_id': 'justintimberlakeVEVO',
582 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
583 'creator': 'Justin Timberlake',
584 'track': 'Tunnel Vision',
585 'artist': 'Justin Timberlake',
590 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
591 'note': 'Embed-only video (#1746)',
595 'upload_date': '20120608',
596 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
597 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
598 'uploader': 'SET India',
599 'uploader_id': 'setindia',
600 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
605 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
606 'note': 'Use the first video ID in the URL',
610 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
611 'uploader': 'Philipp Hagemeister',
612 'uploader_id': 'phihag',
613 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
614 'upload_date': '20121002',
615 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
616 'categories': ['Science & Technology'],
617 'tags': ['youtube-dl'],
621 'dislike_count': int,
624 'skip_download': True,
628 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
629 'note': '256k DASH audio (format 141) via DASH manifest',
633 'upload_date': '20121002',
634 'uploader_id': '8KVIDEO',
635 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
637 'uploader': '8KVIDEO',
638 'title': 'UHDTV TEST 8K VIDEO.mp4'
641 'youtube_include_dash_manifest': True,
644 'skip': 'format 141 not served anymore',
646 # DASH manifest with encrypted signature
648 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
652 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
653 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
655 'uploader': 'AfrojackVEVO',
656 'uploader_id': 'AfrojackVEVO',
657 'upload_date': '20131011',
660 'youtube_include_dash_manifest': True,
661 'format': '141/bestaudio[ext=m4a]',
664 # JS player signature function name containing $
666 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
670 'title': 'Taylor Swift - Shake It Off',
671 'description': 'md5:bec2185232c05479482cb5a9b82719bf',
673 'uploader': 'TaylorSwiftVEVO',
674 'uploader_id': 'TaylorSwiftVEVO',
675 'upload_date': '20140818',
676 'creator': 'Taylor Swift',
679 'youtube_include_dash_manifest': True,
680 'format': '141/bestaudio[ext=m4a]',
685 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
690 'upload_date': '20100909',
691 'uploader': 'Amazing Atheist',
692 'uploader_id': 'TheAmazingAtheist',
693 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
694 'title': 'Burning Everyone\'s Koran',
695 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
698 # Normal age-gate video (No vevo, embed allowed)
700 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
704 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
705 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
707 'uploader': 'The Witcher',
708 'uploader_id': 'WitcherGame',
709 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
710 'upload_date': '20140605',
714 # Age-gate video with encrypted signature
716 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
720 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
721 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
723 'uploader': 'LloydVEVO',
724 'uploader_id': 'LloydVEVO',
725 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
726 'upload_date': '20110629',
730 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
731 # YouTube Red ad is not captured for creator
733 'url': '__2ABJjxzNo',
738 'upload_date': '20100430',
739 'uploader_id': 'deadmau5',
740 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/deadmau5',
741 'creator': 'deadmau5',
742 'description': 'md5:12c56784b8032162bb936a5f76d55360',
743 'uploader': 'deadmau5',
744 'title': 'Deadmau5 - Some Chords (HD)',
745 'alt_title': 'Some Chords',
747 'expected_warnings': [
748 'DASH manifest missing',
751 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
753 'url': 'lqQg6PlCWgI',
758 'upload_date': '20150827',
759 'uploader_id': 'olympic',
760 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
761 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
762 'uploader': 'Olympic',
763 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
766 'skip_download': 'requires avconv',
771 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
775 'stretched_ratio': 16 / 9.,
777 'upload_date': '20110310',
778 'uploader_id': 'AllenMeow',
779 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
780 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
782 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
785 # url_encoded_fmt_stream_map is empty string
787 'url': 'qEJwOuvDf7I',
791 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
793 'upload_date': '20150404',
794 'uploader_id': 'spbelect',
795 'uploader': 'Наблюдатели Петербурга',
798 'skip_download': 'requires avconv',
800 'skip': 'This live event has ended.',
802 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
804 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
808 'title': 'md5:7b81415841e02ecd4313668cde88737a',
809 'description': 'md5:116377fd2963b81ec4ce64b542173306',
811 'upload_date': '20150625',
812 'uploader_id': 'dorappi2000',
813 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
814 'uploader': 'dorappi2000',
815 'formats': 'mincount:31',
817 'skip': 'not actual anymore',
819 # DASH manifest with segment_list
821 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
822 'md5': '8ce563a1d667b599d21064e982ab9e31',
826 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
827 'uploader': 'Airtek',
828 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
829 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
830 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
833 'youtube_include_dash_manifest': True,
834 'format': '135', # bestvideo
836 'skip': 'This live event has ended.',
839 # Multifeed videos (multiple cameras), URL is for Main Camera
840 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
843 'title': 'teamPGP: Rocket League Noob Stream',
844 'description': 'md5:dc7872fb300e143831327f1bae3af010',
850 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
851 'description': 'md5:dc7872fb300e143831327f1bae3af010',
853 'upload_date': '20150721',
854 'uploader': 'Beer Games Beer',
855 'uploader_id': 'beergamesbeer',
856 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
857 'license': 'Standard YouTube License',
863 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
864 'description': 'md5:dc7872fb300e143831327f1bae3af010',
866 'upload_date': '20150721',
867 'uploader': 'Beer Games Beer',
868 'uploader_id': 'beergamesbeer',
869 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
870 'license': 'Standard YouTube License',
876 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
877 'description': 'md5:dc7872fb300e143831327f1bae3af010',
879 'upload_date': '20150721',
880 'uploader': 'Beer Games Beer',
881 'uploader_id': 'beergamesbeer',
882 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
883 'license': 'Standard YouTube License',
889 'title': 'teamPGP: Rocket League Noob Stream (zim)',
890 'description': 'md5:dc7872fb300e143831327f1bae3af010',
892 'upload_date': '20150721',
893 'uploader': 'Beer Games Beer',
894 'uploader_id': 'beergamesbeer',
895 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
896 'license': 'Standard YouTube License',
900 'skip_download': True,
902 'skip': 'This video is not available.',
905 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
906 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
909 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
912 'skip': 'Not multifeed anymore',
915 'url': 'https://vid.plus/FlRa-iH7PGw',
916 'only_matching': True,
919 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
920 'only_matching': True,
923 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
924 # Also tests cut-off URL expansion in video description (see
925 # https://github.com/ytdl-org/youtube-dl/issues/1892,
926 # https://github.com/ytdl-org/youtube-dl/issues/8164)
927 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
931 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
932 'alt_title': 'Dark Walk - Position Music',
933 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
935 'upload_date': '20151119',
936 'uploader_id': 'IronSoulElf',
937 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
938 'uploader': 'IronSoulElf',
939 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
940 'track': 'Dark Walk - Position Music',
941 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
942 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
945 'skip_download': True,
949 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
950 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
951 'only_matching': True,
954 # Video with yt:stretch=17:0
955 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
959 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
960 'description': 'md5:ee18a25c350637c8faff806845bddee9',
961 'upload_date': '20151107',
962 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
963 'uploader': 'CH GAMER DROID',
966 'skip_download': True,
968 'skip': 'This video does not exist.',
971 # Video licensed under Creative Commons
972 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
976 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
977 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
979 'upload_date': '20150127',
980 'uploader_id': 'BerkmanCenter',
981 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
982 'uploader': 'The Berkman Klein Center for Internet & Society',
983 'license': 'Creative Commons Attribution license (reuse allowed)',
986 'skip_download': True,
990 # Channel-like uploader_url
991 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
995 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
996 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
998 'upload_date': '20151119',
999 'uploader': 'Bernie Sanders',
1000 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1001 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1002 'license': 'Creative Commons Attribution license (reuse allowed)',
1005 'skip_download': True,
1009 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1010 'only_matching': True,
1013 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1014 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1015 'only_matching': True,
1018 # Rental video preview
1019 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1021 'id': 'uGpuVWrhIzE',
1023 'title': 'Piku - Trailer',
1024 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1025 'upload_date': '20150811',
1026 'uploader': 'FlixMatrix',
1027 'uploader_id': 'FlixMatrixKaravan',
1028 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1029 'license': 'Standard YouTube License',
1032 'skip_download': True,
1034 'skip': 'This video is not available.',
1037 # YouTube Red video with episode data
1038 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1040 'id': 'iqKdEhx-dD4',
1042 'title': 'Isolation - Mind Field (Ep 1)',
1043 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f',
1045 'upload_date': '20170118',
1046 'uploader': 'Vsauce',
1047 'uploader_id': 'Vsauce',
1048 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1049 'series': 'Mind Field',
1051 'episode_number': 1,
1054 'skip_download': True,
1056 'expected_warnings': [
1057 'Skipping DASH manifest',
1061 # The following content has been identified by the YouTube community
1062 # as inappropriate or offensive to some audiences.
1063 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1065 'id': '6SJNVb0GnPI',
1067 'title': 'Race Differences in Intelligence',
1068 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1070 'upload_date': '20140124',
1071 'uploader': 'New Century Foundation',
1072 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1073 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1076 'skip_download': True,
1081 'url': '1t24XAntNCY',
1082 'only_matching': True,
1085 # geo restricted to JP
1086 'url': 'sJL6WA-aGkQ',
1087 'only_matching': True,
1090 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
1091 'only_matching': True,
1094 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1095 'only_matching': True,
1099 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1100 'only_matching': True,
1103 # Video with unsupported adaptive stream type formats
1104 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1106 'id': 'Z4Vy8R84T1U',
1108 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1109 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1111 'upload_date': '20130923',
1112 'uploader': 'Amelia Putri Harwita',
1113 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1114 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1115 'formats': 'maxcount:10',
1118 'skip_download': True,
1119 'youtube_include_dash_manifest': False,
1123 # Youtube Music Auto-generated description
1124 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1126 'id': 'MgNrAu2pzNs',
1128 'title': 'Voyeur Girl',
1129 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1130 'upload_date': '20190312',
1131 'uploader': 'Various Artists - Topic',
1132 'uploader_id': 'UCVWKBi1ELZn0QX2CBLSkiyw',
1133 'artist': 'Stephen',
1134 'track': 'Voyeur Girl',
1135 'album': 'it\'s too much love to know my dear',
1136 'release_date': '20190313',
1137 'release_year': 2019,
1140 'skip_download': True,
1144 # Youtube Music Auto-generated description
1145 # Retrieve 'artist' field from 'Artist:' in video description
1146 # when it is present on youtube music video
1147 'url': 'https://www.youtube.com/watch?v=k0jLE7tTwjY',
1149 'id': 'k0jLE7tTwjY',
1151 'title': 'Latch Feat. Sam Smith',
1152 'description': 'md5:3cb1e8101a7c85fcba9b4fb41b951335',
1153 'upload_date': '20150110',
1154 'uploader': 'Various Artists - Topic',
1155 'uploader_id': 'UCNkEcmYdjrH4RqtNgh7BZ9w',
1156 'artist': 'Disclosure',
1157 'track': 'Latch Feat. Sam Smith',
1158 'album': 'Latch Featuring Sam Smith',
1159 'release_date': '20121008',
1160 'release_year': 2012,
1163 'skip_download': True,
1167 # Youtube Music Auto-generated description
1168 # handle multiple artists on youtube music video
1169 'url': 'https://www.youtube.com/watch?v=74qn0eJSjpA',
1171 'id': '74qn0eJSjpA',
1173 'title': 'Eastside',
1174 'description': 'md5:290516bb73dcbfab0dcc4efe6c3de5f2',
1175 'upload_date': '20180710',
1176 'uploader': 'Benny Blanco - Topic',
1177 'uploader_id': 'UCzqz_ksRu_WkIzmivMdIS7A',
1178 'artist': 'benny blanco, Halsey, Khalid',
1179 'track': 'Eastside',
1180 'album': 'Eastside',
1181 'release_date': '20180713',
1182 'release_year': 2018,
1185 'skip_download': True,
1189 # Youtube Music Auto-generated description
1190 # handle youtube music video with release_year and no release_date
1191 'url': 'https://www.youtube.com/watch?v=-hcAI0g-f5M',
1193 'id': '-hcAI0g-f5M',
1195 'title': 'Put It On Me',
1196 'description': 'md5:93c55acc682ae7b0c668f2e34e1c069e',
1197 'upload_date': '20180426',
1198 'uploader': 'Matt Maeson - Topic',
1199 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ',
1200 'artist': 'Matt Maeson',
1201 'track': 'Put It On Me',
1202 'album': 'The Hearse',
1203 'release_date': None,
1204 'release_year': 2018,
1207 'skip_download': True,
1212 def __init__(self
, *args
, **kwargs
):
1213 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
1214 self
._player
_cache
= {}
1216 def report_video_info_webpage_download(self
, video_id
):
1217 """Report attempt to download video info webpage."""
1218 self
.to_screen('%s: Downloading video info webpage' % video_id
)
1220 def report_information_extraction(self
, video_id
):
1221 """Report attempt to extract video information."""
1222 self
.to_screen('%s: Extracting video information' % video_id
)
1224 def report_unavailable_format(self
, video_id
, format
):
1225 """Report extracted video URL."""
1226 self
.to_screen('%s: Format %s not available' % (video_id
, format
))
1228 def report_rtmp_download(self
):
1229 """Indicate the download will use the RTMP protocol."""
1230 self
.to_screen('RTMP download detected')
1232 def _signature_cache_id(self
, example_sig
):
1233 """ Return a string representation of a signature """
1234 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
1236 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
1238 r
'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
1241 raise ExtractorError('Cannot identify player %r' % player_url
)
1242 player_type
= id_m
.group('ext')
1243 player_id
= id_m
.group('id')
1245 # Read from filesystem cache
1246 func_id
= '%s_%s_%s' % (
1247 player_type
, player_id
, self
._signature
_cache
_id
(example_sig
))
1248 assert os
.path
.basename(func_id
) == func_id
1250 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
1251 if cache_spec
is not None:
1252 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
1255 'Downloading player %s' % player_url
1256 if self
._downloader
.params
.get('verbose') else
1257 'Downloading %s player %s' % (player_type
, player_id
)
1259 if player_type
== 'js':
1260 code
= self
._download
_webpage
(
1261 player_url
, video_id
,
1263 errnote
='Download of %s failed' % player_url
)
1264 res
= self
._parse
_sig
_js
(code
)
1265 elif player_type
== 'swf':
1266 urlh
= self
._request
_webpage
(
1267 player_url
, video_id
,
1269 errnote
='Download of %s failed' % player_url
)
1271 res
= self
._parse
_sig
_swf
(code
)
1273 assert False, 'Invalid player type %r' % player_type
1275 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1276 cache_res
= res(test_string
)
1277 cache_spec
= [ord(c
) for c
in cache_res
]
1279 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
1282 def _print_sig_code(self
, func
, example_sig
):
1283 def gen_sig_code(idxs
):
1284 def _genslice(start
, end
, step
):
1285 starts
= '' if start
== 0 else str(start
)
1286 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
1287 steps
= '' if step
== 1 else (':%d' % step
)
1288 return 's[%s%s%s]' % (starts
, ends
, steps
)
1291 # Quelch pyflakes warnings - start will be set when step is set
1292 start
= '(Never used)'
1293 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
1294 if step
is not None:
1295 if i
- prev
== step
:
1297 yield _genslice(start
, prev
, step
)
1300 if i
- prev
in [-1, 1]:
1305 yield 's[%d]' % prev
1309 yield _genslice(start
, i
, step
)
1311 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1312 cache_res
= func(test_string
)
1313 cache_spec
= [ord(c
) for c
in cache_res
]
1314 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
1315 signature_id_tuple
= '(%s)' % (
1316 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
1317 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1318 ' return %s\n') % (signature_id_tuple
, expr_code
)
1319 self
.to_screen('Extracted signature function:\n' + code
)
1321 def _parse_sig_js(self
, jscode
):
1322 funcname
= self
._search
_regex
(
1323 (r
'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1324 r
'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1325 r
'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
1327 r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1328 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1329 r'yt\
.akamaized\
.net
/\
)\s
*\|\|\s
*.*?\s
*[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?
:encodeURIComponent\s
*\
()?\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1330 r'\b[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1331 r'\b[a
-zA
-Z0
-9]+\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1332 r'\bc\s
*&&\s
*a\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1333 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1334 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
1335 jscode, 'Initial JS player signature function name
', group='sig
')
1337 jsi = JSInterpreter(jscode)
1338 initial_function = jsi.extract_function(funcname)
1339 return lambda s: initial_function([s])
1341 def _parse_sig_swf(self, file_contents):
1342 swfi = SWFInterpreter(file_contents)
1343 TARGET_CLASSNAME = 'SignatureDecipher
'
1344 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1345 initial_function = swfi.extract_function(searched_class, 'decipher
')
1346 return lambda s: initial_function([s])
1348 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1349 """Turn the encrypted s field into a working signature"""
1351 if player_url is None:
1352 raise ExtractorError('Cannot decrypt signature without player_url
')
1354 if player_url.startswith('//'):
1355 player_url = 'https
:' + player_url
1356 elif not re.match(r'https?
://', player_url):
1357 player_url = compat_urlparse.urljoin(
1358 'https
://www
.youtube
.com
', player_url)
1360 player_id = (player_url, self._signature_cache_id(s))
1361 if player_id not in self._player_cache:
1362 func = self._extract_signature_function(
1363 video_id, player_url, s
1365 self._player_cache[player_id] = func
1366 func = self._player_cache[player_id]
1367 if self._downloader.params.get('youtube_print_sig_code
'):
1368 self._print_sig_code(func, s)
1370 except Exception as e:
1371 tb = traceback.format_exc()
1372 raise ExtractorError(
1373 'Signature extraction failed
: ' + tb, cause=e)
1375 def _get_subtitles(self, video_id, webpage):
1377 subs_doc = self._download_xml(
1378 'https
://video
.google
.com
/timedtext?hl
=en
&type=list&v
=%s' % video_id,
1379 video_id, note=False)
1380 except ExtractorError as err:
1381 self._downloader.report_warning('unable to download video subtitles
: %s' % error_to_compat_str(err))
1385 for track in subs_doc.findall('track
'):
1386 lang = track.attrib['lang_code
']
1387 if lang in sub_lang_list:
1390 for ext in self._SUBTITLE_FORMATS:
1391 params = compat_urllib_parse_urlencode({
1395 'name
': track.attrib['name
'].encode('utf
-8'),
1397 sub_formats.append({
1398 'url
': 'https
://www
.youtube
.com
/api
/timedtext?
' + params,
1401 sub_lang_list[lang] = sub_formats
1402 if not sub_lang_list:
1403 self._downloader.report_warning('video doesn
\'t have subtitles
')
1405 return sub_lang_list
1407 def _get_ytplayer_config(self, video_id, webpage):
1409 # User data may contain arbitrary character sequences that may affect
1410 # JSON extraction with regex, e.g. when '};' is contained the second
1411 # regex won't capture the whole JSON
. Yet working around by trying more
1412 # concrete regex first keeping in mind proper quoted string handling
1413 # to be implemented in future that will replace this workaround (see
1414 # https://github.com/ytdl-org/youtube-dl/issues/7468,
1415 # https://github.com/ytdl-org/youtube-dl/pull/7599)
1416 r
';ytplayer\.config\s*=\s*({.+?});ytplayer',
1417 r
';ytplayer\.config\s*=\s*({.+?});',
1419 config
= self
._search
_regex
(
1420 patterns
, webpage
, 'ytplayer.config', default
=None)
1422 return self
._parse
_json
(
1423 uppercase_escape(config
), video_id
, fatal
=False)
1425 def _get_automatic_captions(self
, video_id
, webpage
):
1426 """We need the webpage for getting the captions url, pass it as an
1427 argument to speed up the process."""
1428 self
.to_screen('%s: Looking for automatic captions' % video_id
)
1429 player_config
= self
._get
_ytplayer
_config
(video_id
, webpage
)
1430 err_msg
= 'Couldn\'t find automatic captions for %s' % video_id
1431 if not player_config
:
1432 self
._downloader
.report_warning(err_msg
)
1435 args
= player_config
['args']
1436 caption_url
= args
.get('ttsurl')
1438 timestamp
= args
['timestamp']
1439 # We get the available subtitles
1440 list_params
= compat_urllib_parse_urlencode({
1445 list_url
= caption_url
+ '&' + list_params
1446 caption_list
= self
._download
_xml
(list_url
, video_id
)
1447 original_lang_node
= caption_list
.find('track')
1448 if original_lang_node
is None:
1449 self
._downloader
.report_warning('Video doesn\'t have automatic captions')
1451 original_lang
= original_lang_node
.attrib
['lang_code']
1452 caption_kind
= original_lang_node
.attrib
.get('kind', '')
1455 for lang_node
in caption_list
.findall('target'):
1456 sub_lang
= lang_node
.attrib
['lang_code']
1458 for ext
in self
._SUBTITLE
_FORMATS
:
1459 params
= compat_urllib_parse_urlencode({
1460 'lang': original_lang
,
1464 'kind': caption_kind
,
1466 sub_formats
.append({
1467 'url': caption_url
+ '&' + params
,
1470 sub_lang_list
[sub_lang
] = sub_formats
1471 return sub_lang_list
1473 def make_captions(sub_url
, sub_langs
):
1474 parsed_sub_url
= compat_urllib_parse_urlparse(sub_url
)
1475 caption_qs
= compat_parse_qs(parsed_sub_url
.query
)
1477 for sub_lang
in sub_langs
:
1479 for ext
in self
._SUBTITLE
_FORMATS
:
1481 'tlang': [sub_lang
],
1484 sub_url
= compat_urlparse
.urlunparse(parsed_sub_url
._replace
(
1485 query
=compat_urllib_parse_urlencode(caption_qs
, True)))
1486 sub_formats
.append({
1490 captions
[sub_lang
] = sub_formats
1493 # New captions format as of 22.06.2017
1494 player_response
= args
.get('player_response')
1495 if player_response
and isinstance(player_response
, compat_str
):
1496 player_response
= self
._parse
_json
(
1497 player_response
, video_id
, fatal
=False)
1499 renderer
= player_response
['captions']['playerCaptionsTracklistRenderer']
1500 base_url
= renderer
['captionTracks'][0]['baseUrl']
1502 for lang
in renderer
['translationLanguages']:
1503 lang_code
= lang
.get('languageCode')
1505 sub_lang_list
.append(lang_code
)
1506 return make_captions(base_url
, sub_lang_list
)
1508 # Some videos don't provide ttsurl but rather caption_tracks and
1509 # caption_translation_languages (e.g. 20LmZk1hakA)
1510 # Does not used anymore as of 22.06.2017
1511 caption_tracks
= args
['caption_tracks']
1512 caption_translation_languages
= args
['caption_translation_languages']
1513 caption_url
= compat_parse_qs(caption_tracks
.split(',')[0])['u'][0]
1515 for lang
in caption_translation_languages
.split(','):
1516 lang_qs
= compat_parse_qs(compat_urllib_parse_unquote_plus(lang
))
1517 sub_lang
= lang_qs
.get('lc', [None])[0]
1519 sub_lang_list
.append(sub_lang
)
1520 return make_captions(caption_url
, sub_lang_list
)
1521 # An extractor error can be raise by the download process if there are
1522 # no automatic captions but there are subtitles
1523 except (KeyError, IndexError, ExtractorError
):
1524 self
._downloader
.report_warning(err_msg
)
1527 def _mark_watched(self
, video_id
, video_info
, player_response
):
1528 playback_url
= url_or_none(try_get(
1530 lambda x
: x
['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1531 video_info
, lambda x
: x
['videostats_playback_base_url'][0]))
1532 if not playback_url
:
1534 parsed_playback_url
= compat_urlparse
.urlparse(playback_url
)
1535 qs
= compat_urlparse
.parse_qs(parsed_playback_url
.query
)
1537 # cpn generation algorithm is reverse engineered from base.js.
1538 # In fact it works even with dummy cpn.
1539 CPN_ALPHABET
= 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1540 cpn
= ''.join((CPN_ALPHABET
[random
.randint(0, 256) & 63] for _
in range(0, 16)))
1546 playback_url
= compat_urlparse
.urlunparse(
1547 parsed_playback_url
._replace
(query
=compat_urllib_parse_urlencode(qs
, True)))
1549 self
._download
_webpage
(
1550 playback_url
, video_id
, 'Marking watched',
1551 'Unable to mark watched', fatal
=False)
1554 def _extract_urls(webpage
):
1555 # Embedded YouTube player
1557 unescapeHTML(mobj
.group('url'))
1558 for mobj
in re
.finditer(r
'''(?x)
1568 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
1569 (?
:embed|v|p
)/[0-9A
-Za
-z_
-]{11}
.*?
)
1572 # lazyYT YouTube embed
1573 entries.extend(list(map(
1575 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1577 # Wordpress "YouTube Video Importer" plugin
1578 matches = re.findall(r'''(?x
)<div
[^
>]+
1579 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
1580 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage)
1581 entries.extend(m[-1] for m in matches)
1586 def _extract_url(webpage):
1587 urls = YoutubeIE._extract_urls(webpage)
1588 return urls[0] if urls else None
1591 def extract_id(cls, url):
1592 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1594 raise ExtractorError('Invalid URL: %s' % url)
1595 video_id = mobj.group(2)
1598 def _extract_annotations(self, video_id):
1599 return self._download_webpage(
1600 'https://www.youtube.com/annotations_invideo', video_id,
1601 note='Downloading annotations',
1602 errnote='Unable to download video annotations', fatal=False,
1606 'video_id': video_id,
1610 def _extract_chapters(description, duration):
1613 chapter_lines = re.findall(
1614 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\
.www\
.watch\
.player\
.seekTo
[^
>]+>(\d{1,2}
:\d{1,2}
(?
::\d{1,2}
)?
)</a
>[^
>]*)(?
=$|
<br\s
*/>)',
1616 if not chapter_lines:
1619 for next_num, (chapter_line, time_point) in enumerate(
1620 chapter_lines, start=1):
1621 start_time = parse_duration(time_point)
1622 if start_time is None:
1624 if start_time > duration:
1626 end_time = (duration if next_num == len(chapter_lines)
1627 else parse_duration(chapter_lines[next_num][1]))
1628 if end_time is None:
1630 if end_time > duration:
1632 if start_time > end_time:
1634 chapter_title = re.sub(
1635 r'<a
[^
>]+>[^
<]+</a
>', '', chapter_line).strip(' \t-')
1636 chapter_title = re.sub(r'\s
+', ' ', chapter_title)
1638 'start_time
': start_time,
1639 'end_time
': end_time,
1640 'title
': chapter_title,
1644 def _real_extract(self, url):
1645 url, smuggled_data = unsmuggle_url(url, {})
1648 'http
' if self._downloader.params.get('prefer_insecure
', False)
1653 parsed_url = compat_urllib_parse_urlparse(url)
1654 for component in [parsed_url.fragment, parsed_url.query]:
1655 query = compat_parse_qs(component)
1656 if start_time is None and 't
' in query:
1657 start_time = parse_duration(query['t
'][0])
1658 if start_time is None and 'start
' in query:
1659 start_time = parse_duration(query['start
'][0])
1660 if end_time is None and 'end
' in query:
1661 end_time = parse_duration(query['end
'][0])
1663 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1664 mobj = re.search(self._NEXT_URL_RE, url)
1666 url = proto + '://www
.youtube
.com
/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1667 video_id = self.extract_id(url)
1670 url = proto + '://www
.youtube
.com
/watch?v
=%s&gl
=US
&hl
=en
&has_verified
=1&bpctr
=9999999999' % video_id
1671 video_webpage = self._download_webpage(url, video_id)
1673 # Attempt to extract SWF player URL
1674 mobj = re.search(r'swfConfig
.*?
"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1675 if mobj is not None:
1676 player_url = re.sub(r'\\(.)', r'\
1', mobj.group(1))
1682 def add_dash_mpd(video_info):
1683 dash_mpd = video_info.get('dashmpd
')
1684 if dash_mpd and dash_mpd[0] not in dash_mpds:
1685 dash_mpds.append(dash_mpd[0])
1687 def add_dash_mpd_pr(pl_response):
1688 dash_mpd = url_or_none(try_get(
1689 pl_response, lambda x: x['streamingData
']['dashManifestUrl
'],
1691 if dash_mpd and dash_mpd not in dash_mpds:
1692 dash_mpds.append(dash_mpd)
1697 def extract_view_count(v_info):
1698 return int_or_none(try_get(v_info, lambda x: x['view_count
'][0]))
1700 def extract_token(v_info):
1701 return dict_get(v_info, ('account_playback_token
', 'accountPlaybackToken
', 'token
'))
1703 def extract_player_response(player_response, video_id):
1704 pl_response = str_or_none(player_response)
1707 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1708 if isinstance(pl_response, dict):
1709 add_dash_mpd_pr(pl_response)
1712 player_response = {}
1715 embed_webpage = None
1716 if re.search(r'player
-age
-gate
-content
">', video_webpage) is not None:
1718 # We simulate the access to the video from www.youtube.com/v/{video_id}
1719 # this can be viewed without login into Youtube
1720 url = proto + '://www.youtube.com/embed/%s' % video_id
1721 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1722 data = compat_urllib_parse_urlencode({
1723 'video_id': video_id,
1724 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1725 'sts': self._search_regex(
1726 r'"sts
"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
1728 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
1729 video_info_webpage = self._download_webpage(
1730 video_info_url, video_id,
1731 note='Refetching age-gated info webpage',
1732 errnote='unable to download video info webpage')
1733 video_info = compat_parse_qs(video_info_webpage)
1734 pl_response = video_info.get('player_response', [None])[0]
1735 player_response = extract_player_response(pl_response, video_id)
1736 add_dash_mpd(video_info)
1737 view_count = extract_view_count(video_info)
1742 # Try looking directly into the video webpage
1743 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1745 args = ytplayer_config['args']
1746 if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'):
1747 # Convert to the same format returned by compat_parse_qs
1748 video_info = dict((k, [v]) for k, v in args.items())
1749 add_dash_mpd(video_info)
1750 # Rental video is not rented but preview is available (e.g.
1751 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1752 # https://github.com/ytdl-org/youtube-dl/issues/10532)
1753 if not video_info and args.get('ypc_vid'):
1754 return self.url_result(
1755 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
1756 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1758 sts = ytplayer_config.get('sts')
1759 if not player_response:
1760 player_response = extract_player_response(args.get('player_response'), video_id)
1761 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1762 add_dash_mpd_pr(player_response)
1763 # We also try looking in get_video_info since it may contain different dashmpd
1764 # URL that points to a DASH manifest with possibly different itag set (some itags
1765 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1766 # manifest pointed by get_video_info's dashmpd).
1767 # The general idea is to take a union of itags of both DASH manifests (for example
1768 # video with such 'manifest behavior' see https://github.com/ytdl-org/youtube-dl/issues/6093)
1769 self.report_video_info_webpage_download(video_id)
1770 for el in ('embedded', 'detailpage', 'vevo', ''):
1772 'video_id': video_id,
1782 video_info_webpage = self._download_webpage(
1783 '%s://www.youtube.com/get_video_info' % proto,
1784 video_id, note=False,
1785 errnote='unable to download video info webpage',
1786 fatal=False, query=query)
1787 if not video_info_webpage:
1789 get_video_info = compat_parse_qs(video_info_webpage)
1790 if not player_response:
1791 pl_response = get_video_info.get('player_response', [None])[0]
1792 player_response = extract_player_response(pl_response, video_id)
1793 add_dash_mpd(get_video_info)
1794 if view_count is None:
1795 view_count = extract_view_count(get_video_info)
1797 video_info = get_video_info
1798 get_token = extract_token(get_video_info)
1800 # Different get_video_info requests may report different results, e.g.
1801 # some may report video unavailability, but some may serve it without
1802 # any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362,
1803 # the original webpage as well as el=info and el=embedded get_video_info
1804 # requests report video unavailability due to geo restriction while
1805 # el=detailpage succeeds and returns valid data). This is probably
1806 # due to YouTube measures against IP ranges of hosting providers.
1807 # Working around by preferring the first succeeded video_info containing
1808 # the token if no such video_info yet was found.
1809 token = extract_token(video_info)
1811 video_info = get_video_info
1814 def extract_unavailable_message():
1815 return self._html_search_regex(
1816 r'(?s)<h1[^>]+id="unavailable
-message
"[^>]*>(.+?)</h1>',
1817 video_webpage, 'unavailable message', default=None)
1820 unavailable_message = extract_unavailable_message()
1821 if not unavailable_message:
1822 unavailable_message = 'Unable to extract video data'
1823 raise ExtractorError(
1824 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
1826 video_details = try_get(
1827 player_response, lambda x: x['videoDetails'], dict) or {}
1829 video_title = video_info.get('title', [None])[0] or video_details.get('title')
1831 self._downloader.report_warning('Unable to extract video title')
1834 description_original = video_description = get_element_by_id("eow
-description
", video_webpage)
1835 if video_description:
1838 redir_url = compat_urlparse.urljoin(url, m.group(1))
1839 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1840 if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
1841 qs = compat_parse_qs(parsed_redir_url.query)
1847 description_original = video_description = re.sub(r'''(?x)
1849 (?:[a-zA-Z-]+="[^
"]*"\s
+)*?
1850 (?
:title|href
)="([^"]+)"\s+
1851 (?:[a-zA-Z-]+="[^
"]*"\s
+)*?
1855 ''', replace_url, video_description)
1856 video_description = clean_html(video_description)
1858 video_description = self._html_search_meta('description', video_webpage) or video_details.get('shortDescription')
1860 if not smuggled_data.get('force_singlefeed', False):
1861 if not self._downloader.params.get('noplaylist'):
1862 multifeed_metadata_list = try_get(
1864 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
1865 compat_str) or try_get(
1866 video_info, lambda x: x['multifeed_metadata_list'][0], compat_str)
1867 if multifeed_metadata_list:
1870 for feed in multifeed_metadata_list.split(','):
1871 # Unquote should take place before split on comma (,) since textual
1872 # fields may contain comma as well (see
1873 # https://github.com/ytdl-org/youtube-dl/issues/8536)
1874 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1876 '_type': 'url_transparent',
1877 'ie_key': 'Youtube',
1879 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1880 {'force_singlefeed': True}),
1881 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1883 feed_ids.append(feed_data['id'][0])
1885 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1886 % (', '.join(feed_ids), video_id))
1887 return self.playlist_result(entries, video_id, video_title, video_description)
1889 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1891 if view_count is None:
1892 view_count = extract_view_count(video_info)
1893 if view_count is None and video_details:
1894 view_count = int_or_none(video_details.get('viewCount'))
1897 is_live = bool_or_none(video_details.get('isLive'))
1899 # Check for "rental
" videos
1900 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
1901 raise ExtractorError('"rental
" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True)
1903 def _extract_filesize(media_url):
1904 return int_or_none(self._search_regex(
1905 r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
1907 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1908 self.report_rtmp_download()
1910 'format_id': '_rtmp',
1912 'url': video_info['conn'][0],
1913 'player_url': player_url,
1915 elif not is_live and (len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1):
1916 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
1917 if 'rtmpe%3Dyes' in encoded_url_map:
1918 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True)
1920 fmt_list = video_info.get('fmt_list', [''])[0]
1922 for fmt in fmt_list.split(','):
1923 spec = fmt.split('/')
1925 width_height = spec[1].split('x')
1926 if len(width_height) == 2:
1927 formats_spec[spec[0]] = {
1928 'resolution': spec[1],
1929 'width': int_or_none(width_height[0]),
1930 'height': int_or_none(width_height[1]),
1932 q = qualities(['small', 'medium', 'hd720'])
1933 streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list)
1934 if streaming_formats:
1935 for fmt in streaming_formats:
1936 itag = str_or_none(fmt.get('itag'))
1939 quality = fmt.get('quality')
1940 quality_label = fmt.get('qualityLabel') or quality
1941 formats_spec[itag] = {
1942 'asr': int_or_none(fmt.get('audioSampleRate')),
1943 'filesize': int_or_none(fmt.get('contentLength')),
1944 'format_note': quality_label,
1945 'fps': int_or_none(fmt.get('fps')),
1946 'height': int_or_none(fmt.get('height')),
1947 'quality': q(quality),
1948 # bitrate for itag 43 is always 2147483647
1949 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None,
1950 'width': int_or_none(fmt.get('width')),
1953 for url_data_str in encoded_url_map.split(','):
1954 url_data = compat_parse_qs(url_data_str)
1955 if 'itag' not in url_data or 'url' not in url_data or url_data.get('drm_families'):
1957 stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
1958 # Unsupported FORMAT_STREAM_TYPE_OTF
1959 if stream_type == 3:
1961 format_id = url_data['itag'][0]
1962 url = url_data['url'][0]
1964 if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
1965 ASSETS_RE = r'"assets
":.+?"js
":\s*("[^
"]+")'
1966 jsplayer_url_json = self._search_regex(
1968 embed_webpage if age_gate else video_webpage,
1969 'JS player
URL (1)', default=None)
1970 if not jsplayer_url_json and not age_gate:
1971 # We need the embed website after all
1972 if embed_webpage is None:
1973 embed_url = proto + '://www
.youtube
.com
/embed
/%s' % video_id
1974 embed_webpage = self._download_webpage(
1975 embed_url, video_id, 'Downloading embed webpage
')
1976 jsplayer_url_json = self._search_regex(
1977 ASSETS_RE, embed_webpage, 'JS player URL
')
1979 player_url = json.loads(jsplayer_url_json)
1980 if player_url is None:
1981 player_url_json = self._search_regex(
1982 r'ytplayer\
.config
.*?
"url"\s
*:\s
*("[^"]+")',
1983 video_webpage, 'age gate player URL')
1984 player_url = json.loads(player_url_json)
1986 if 'sig' in url_data:
1987 url += '&signature=' + url_data['sig'][0]
1988 elif 's' in url_data:
1989 encrypted_sig = url_data['s'][0]
1991 if self._downloader.params.get('verbose'):
1992 if player_url is None:
1993 player_version = 'unknown'
1994 player_desc = 'unknown'
1996 if player_url.endswith('swf'):
1997 player_version = self._search_regex(
1998 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
1999 'flash player', fatal=False)
2000 player_desc = 'flash player %s' % player_version
2002 player_version = self._search_regex(
2003 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
2004 r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
2006 'html5 player', fatal=False)
2007 player_desc = 'html5 player %s' % player_version
2009 parts_sizes = self._signature_cache_id(encrypted_sig)
2010 self.to_screen('{%s} signature length %s, %s' %
2011 (format_id, parts_sizes, player_desc))
2013 signature = self._decrypt_signature(
2014 encrypted_sig, video_id, player_url, age_gate)
2015 sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature'
2016 url += '&%s=%s' % (sp, signature)
2017 if 'ratebypass' not in url:
2018 url += '&ratebypass=yes'
2021 'format_id': format_id,
2023 'player_url': player_url,
2025 if format_id in self._formats:
2026 dct.update(self._formats[format_id])
2027 if format_id in formats_spec:
2028 dct.update(formats_spec[format_id])
2030 # Some itags are not included in DASH manifest thus corresponding formats will
2031 # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993).
2032 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
2033 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
2034 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
2036 filesize = int_or_none(url_data.get(
2037 'clen', [None])[0]) or _extract_filesize(url)
2039 quality = url_data.get('quality', [None])[0]
2042 'filesize': filesize,
2043 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
2046 'fps': int_or_none(url_data.get('fps', [None])[0]),
2047 'format_note': url_data.get('quality_label', [None])[0] or quality,
2048 'quality': q(quality),
2050 for key, value in more_fields.items():
2053 type_ = url_data.get('type', [None])[0]
2055 type_split = type_.split(';')
2056 kind_ext = type_split[0].split('/')
2057 if len(kind_ext) == 2:
2059 dct['ext'] = mimetype2ext(type_split[0])
2060 if kind in ('audio', 'video'):
2062 for mobj in re.finditer(
2063 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?
)(?P
<val
>.+?
)(?P
=quote
)(?
:;|$
)', type_):
2064 if mobj.group('key
') == 'codecs
':
2065 codecs = mobj.group('val
')
2068 dct.update(parse_codecs(codecs))
2069 if dct.get('acodec
') == 'none
' or dct.get('vcodec
') == 'none
':
2070 dct['downloader_options
'] = {
2071 # Youtube throttles chunks >~10M
2072 'http_chunk_size
': 10485760,
2077 url_or_none(try_get(
2079 lambda x: x['streamingData
']['hlsManifestUrl
'],
2081 or url_or_none(try_get(
2082 video_info, lambda x: x['hlsvp
'][0], compat_str)))
2085 m3u8_formats = self._extract_m3u8_formats(
2086 manifest_url, video_id, 'mp4
', fatal=False)
2087 for a_format in m3u8_formats:
2088 itag = self._search_regex(
2089 r'/itag
/(\d
+)/', a_format['url
'], 'itag
', default=None)
2091 a_format['format_id
'] = itag
2092 if itag in self._formats:
2093 dct = self._formats[itag].copy()
2094 dct.update(a_format)
2096 a_format['player_url
'] = player_url
2097 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
2098 a_format.setdefault('http_headers
', {})['Youtubedl
-no
-compression
'] = 'True'
2099 formats.append(a_format)
2101 error_message = clean_html(video_info.get('reason
', [None])[0])
2102 if not error_message:
2103 error_message = extract_unavailable_message()
2105 raise ExtractorError(error_message, expected=True)
2106 raise ExtractorError('no conn
, hlsvp
, hlsManifestUrl
or url_encoded_fmt_stream_map information found
in video info
')
2109 video_uploader = try_get(
2110 video_info, lambda x: x['author
'][0],
2111 compat_str) or str_or_none(video_details.get('author
'))
2113 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
2115 self._downloader.report_warning('unable to extract uploader name
')
2118 video_uploader_id = None
2119 video_uploader_url = None
2121 r'<link itemprop
="url" href
="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
2123 if mobj is not None:
2124 video_uploader_id = mobj.group('uploader_id')
2125 video_uploader_url = mobj.group('uploader_url')
2127 self._downloader.report_warning('unable to extract uploader nickname')
2130 str_or_none(video_details.get('channelId'))
2131 or self._html_search_meta(
2132 'channelId', video_webpage, 'channel id', default=None)
2133 or self._search_regex(
2134 r'data-channel-external-id=(["\'])(?P
<id>(?
:(?
!\
1).)+)\
1',
2135 video_webpage, 'channel
id', default=None, group='id'))
2136 channel_url = 'http
://www
.youtube
.com
/channel
/%s' % channel_id if channel_id else None
2139 # We try first to get a high quality image:
2140 m_thumb = re.search(r'<span itemprop
="thumbnail".*?href
="(.*?)">',
2141 video_webpage, re.DOTALL)
2142 if m_thumb is not None:
2143 video_thumbnail = m_thumb.group(1)
2144 elif 'thumbnail_url
' not in video_info:
2145 self._downloader.report_warning('unable to extract video thumbnail
')
2146 video_thumbnail = None
2147 else: # don't panic
if we can
't find it
2148 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url
'][0])
2151 upload_date = self._html_search_meta(
2152 'datePublished
', video_webpage, 'upload date
', default=None)
2154 upload_date = self._search_regex(
2155 [r'(?s
)id="eow-date.*?>(.*?)</span>',
2156 r'(?:id="watch
-uploader
-info
".*?>.*?|["\']simpleText
["\']\s*:\s*["\'])(?
:Published|Uploaded|Streamed live|Started
) on (.+?
)[<"\']'],
2157 video_webpage, 'upload date', default=None)
2158 upload_date = unified_strdate(upload_date)
2160 video_license = self._html_search_regex(
2161 r'<h4[^>]+class="title
"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
2162 video_webpage, 'license', default=None)
2164 m_music = re.search(
2166 <h4[^>]+class="title
"[^>]*>\s*Music\s*</h4>\s*
2174 \bhref=["\']/red
[^
>]*>|
# drop possible
2175 >\s
*Listen ad
-free
with YouTube Red
# YouTube Red ad
2182 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
2183 video_creator = clean_html(m_music.group('creator'))
2185 video_alt_title = video_creator = None
2187 def extract_meta(field):
2188 return self._html_search_regex(
2189 r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
2190 video_webpage, field, default=None)
2192 track = extract_meta('Song')
2193 artist = extract_meta('Artist')
2194 album = extract_meta('Album')
2196 # Youtube Music Auto-generated description
2197 release_date = release_year = None
2198 if video_description:
2199 mobj = re.search(r'(?s)Provided to YouTube by [^\n]+\n+(?P<track>[^·]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?', video_description)
2202 track = mobj.group('track').strip()
2204 artist = mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·'))
2206 album = mobj.group('album'.strip())
2207 release_year = mobj.group('release_year')
2208 release_date = mobj.group('release_date')
2210 release_date = release_date.replace('-', '')
2211 if not release_year:
2212 release_year = int(release_date[:4])
2214 release_year = int(release_year)
2216 m_episode = re.search(
2217 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
2220 series = unescapeHTML(m_episode.group('series'))
2221 season_number = int(m_episode.group('season'))
2222 episode_number = int(m_episode.group('episode'))
2224 series = season_number = episode_number = None
2226 m_cat_container = self._search_regex(
2227 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
2228 video_webpage, 'categories', default=None)
2230 category = self._html_search_regex(
2231 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
2233 video_categories = None if category is None else [category]
2235 video_categories = None
2238 unescapeHTML(m.group('content'))
2239 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
2241 def _extract_count(count_name):
2242 return str_to_int(self._search_regex(
2243 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
2244 % re.escape(count_name),
2245 video_webpage, count_name, default=None))
2247 like_count = _extract_count('like')
2248 dislike_count = _extract_count('dislike')
2250 if view_count is None:
2251 view_count = str_to_int(self._search_regex(
2252 r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2253 'view count', default=None))
2256 float_or_none(video_details.get('averageRating'))
2257 or try_get(video_info, lambda x: float_or_none(x['avg_rating'][0])))
2260 video_subtitles = self.extract_subtitles(video_id, video_webpage)
2261 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
2263 video_duration = try_get(
2264 video_info, lambda x: int_or_none(x['length_seconds'][0]))
2265 if not video_duration:
2266 video_duration = int_or_none(video_details.get('lengthSeconds'))
2267 if not video_duration:
2268 video_duration = parse_duration(self._html_search_meta(
2269 'duration', video_webpage, 'video duration'))
2272 video_annotations = None
2273 if self._downloader.params.get('writeannotations', False):
2274 video_annotations = self._extract_annotations(video_id)
2276 chapters = self._extract_chapters(description_original, video_duration)
2278 # Look for the DASH manifest
2279 if self._downloader.params.get('youtube_include_dash_manifest', True):
2280 dash_mpd_fatal = True
2281 for mpd_url in dash_mpds:
2284 def decrypt_sig(mobj):
2286 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2287 return '/signature/%s' % dec_s
2289 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2291 for df in self._extract_mpd_formats(
2292 mpd_url, video_id, fatal=dash_mpd_fatal,
2293 formats_dict=self._formats):
2294 if not df.get('filesize'):
2295 df['filesize'] = _extract_filesize(df['url'])
2296 # Do not overwrite DASH format found in some previous DASH manifest
2297 if df['format_id'] not in dash_formats:
2298 dash_formats[df['format_id']] = df
2299 # Additional DASH manifests may end up in HTTP Error 403 therefore
2300 # allow them to fail without bug report message if we already have
2301 # some DASH manifest succeeded. This is temporary workaround to reduce
2302 # burst of bug reports until we figure out the reason and whether it
2303 # can be fixed at all.
2304 dash_mpd_fatal = False
2305 except (ExtractorError, KeyError) as e:
2306 self.report_warning(
2307 'Skipping DASH manifest: %r' % e, video_id)
2309 # Remove the formats we found through non-DASH, they
2310 # contain less info and it can be wrong, because we use
2311 # fixed values (for example the resolution). See
2312 # https://github.com/ytdl-org/youtube-dl/issues/5774 for an
2314 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
2315 formats.extend(dash_formats.values())
2317 # Check for malformed aspect ratio
2318 stretched_m = re.search(
2319 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2322 w = float(stretched_m.group('w'))
2323 h = float(stretched_m.group('h'))
2324 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2325 # We will only process correct ratios.
2329 if f.get('vcodec') != 'none':
2330 f['stretched_ratio'] = ratio
2333 token = extract_token(video_info)
2335 if 'reason' in video_info:
2336 if 'The uploader has not made this video available in your country.' in video_info['reason']:
2337 regions_allowed = self._html_search_meta(
2338 'regionsAllowed', video_webpage, default=None)
2339 countries = regions_allowed.split(',') if regions_allowed else None
2340 self.raise_geo_restricted(
2341 msg=video_info['reason'][0], countries=countries)
2342 reason = video_info['reason'][0]
2343 if 'Invalid parameters' in reason:
2344 unavailable_message = extract_unavailable_message()
2345 if unavailable_message:
2346 reason = unavailable_message
2347 raise ExtractorError(
2348 'YouTube said: %s' % reason,
2349 expected=True, video_id=video_id)
2351 raise ExtractorError(
2352 '"token" parameter not in video info for unknown reason',
2355 if not formats and (video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos'])):
2356 raise ExtractorError('This video is DRM protected.', expected=True)
2358 self._sort_formats(formats)
2360 self.mark_watched(video_id, video_info, player_response)
2364 'uploader': video_uploader,
2365 'uploader_id': video_uploader_id,
2366 'uploader_url': video_uploader_url,
2367 'channel_id': channel_id,
2368 'channel_url': channel_url,
2369 'upload_date': upload_date,
2370 'license': video_license,
2371 'creator': video_creator or artist,
2372 'title': video_title,
2373 'alt_title': video_alt_title or track,
2374 'thumbnail': video_thumbnail,
2375 'description': video_description,
2376 'categories': video_categories,
2378 'subtitles': video_subtitles,
2379 'automatic_captions': automatic_captions,
2380 'duration': video_duration,
2381 'age_limit': 18 if age_gate else 0,
2382 'annotations': video_annotations,
2383 'chapters': chapters,
2384 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
2385 'view_count': view_count,
2386 'like_count': like_count,
2387 'dislike_count': dislike_count,
2388 'average_rating': average_rating,
2391 'start_time': start_time,
2392 'end_time': end_time,
2394 'season_number': season_number,
2395 'episode_number': episode_number,
2399 'release_date': release_date,
2400 'release_year': release_year,
2404 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
2405 IE_DESC = 'YouTube.com playlists'
2406 _VALID_URL = r"""(?x)(?:
2416 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
2417 \? (?:.*?[&;])*? (?:p|a|list)=
2420 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
2423 (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,}
2424 # Top tracks, they can also include dots
2430 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
2431 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
2432 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:&(?:[^"]*?index=(?P<index>\d+))?(?:[^>]+>(?P<title>[^<]+))?)?'
2433 IE_NAME = 'youtube:playlist'
2435 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2437 'title': 'ytdl test PL',
2438 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2440 'playlist_count': 3,
2442 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2444 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2445 'title': 'YDL_Empty_List',
2447 'playlist_count': 0,
2448 'skip': 'This playlist is private',
2450 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2451 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2453 'title': '29C3: Not my department',
2454 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2455 'uploader': 'Christiaan008',
2456 'uploader_id': 'ChRiStIaAn008',
2458 'playlist_count': 95,
2460 'note': 'issue #673',
2461 'url': 'PLBB231211A4F62143',
2463 'title': '[OLD]Team Fortress 2 (Class-based LP)',
2464 'id': 'PLBB231211A4F62143',
2465 'uploader': 'Wickydoo',
2466 'uploader_id': 'Wickydoo',
2468 'playlist_mincount': 26,
2470 'note': 'Large playlist',
2471 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2473 'title': 'Uploads from Cauchemar',
2474 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2475 'uploader': 'Cauchemar',
2476 'uploader_id': 'Cauchemar89',
2478 'playlist_mincount': 799,
2480 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2482 'title': 'YDL_safe_search',
2483 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2485 'playlist_count': 2,
2486 'skip': 'This playlist is private',
2489 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2490 'playlist_count': 4,
2493 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2494 'uploader': 'milan',
2495 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
2498 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2499 'playlist_mincount': 485,
2501 'title': '2018 Chinese New Singles (11/6 updated)',
2502 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2504 'uploader_id': 'sdragonfang',
2507 'note': 'Embedded SWF player',
2508 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
2509 'playlist_count': 4,
2512 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
2514 'skip': 'This playlist does not exist',
2516 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2517 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2519 'title': 'Uploads from Interstellar Movie',
2520 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2521 'uploader': 'Interstellar Movie',
2522 'uploader_id': 'InterstellarMovie1',
2524 'playlist_mincount': 21,
2526 # Playlist URL that does not actually serve a playlist
2527 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2529 'id': 'FqZTN594JQw',
2531 'title': "Smiley's People 01 detective, Adventure Series, Action",
2532 'uploader': 'STREEM',
2533 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2534 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2535 'upload_date': '20150526',
2536 'license': 'Standard YouTube License',
2537 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2538 'categories': ['People & Blogs'],
2542 'dislike_count': int,
2545 'skip_download': True,
2547 'skip': 'This video is not available.',
2548 'add_ie': [YoutubeIE.ie_key()],
2550 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2552 'id': 'yeWKywCrFtk',
2554 'title': 'Small Scale Baler and Braiding Rugs',
2555 'uploader': 'Backus-Page House Museum',
2556 'uploader_id': 'backuspagemuseum',
2557 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
2558 'upload_date': '20161008',
2559 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2560 'categories': ['Nonprofits & Activism'],
2563 'dislike_count': int,
2567 'skip_download': True,
2570 # https://github.com/ytdl-org/youtube-dl/issues/21844
2571 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2573 'title': 'Data Analysis with Dr Mike Pound',
2574 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2575 'uploader_id': 'Computerphile',
2576 'uploader': 'Computerphile',
2578 'playlist_mincount': 11,
2580 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2581 'only_matching': True,
2583 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2584 'only_matching': True,
2586 # music album playlist
2587 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
2588 'only_matching': True,
2590 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
2591 'only_matching': True,
2594 def _real_initialize(self):
2597 def _extract_mix(self, playlist_id):
2598 # The mixes are generated from a single video
2599 # the id of the playlist is just 'RD' + video_id
2601 last_id = playlist_id[-11:]
2602 for n in itertools.count(1):
2603 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2604 webpage = self._download_webpage(
2605 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2606 new_ids = orderedSet(re.findall(
2607 r'''(?xs
)data
-video
-username
=".*?".*?
2608 href
="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?
list=%s''' % re.escape(playlist_id),
2610 # Fetch new pages until all the videos are repeated, it seems that
2611 # there are always 51 unique videos.
2612 new_ids = [_id for _id in new_ids if _id not in ids]
2618 url_results = self._ids_to_results(ids)
2620 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
2622 search_title('playlist-title')
2623 or search_title('title long-title')
2624 or search_title('title'))
2625 title = clean_html(title_span)
2627 return self.playlist_result(url_results, playlist_id, title)
2629 def _extract_playlist(self, playlist_id):
2630 url = self._TEMPLATE_URL % playlist_id
2631 page = self._download_webpage(url, playlist_id)
2633 # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604)
2634 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
2635 match = match.strip()
2636 # Check if the playlist exists or is private
2637 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2639 reason = mobj.group('reason')
2640 message = 'This playlist %s' % reason
2641 if 'private' in reason:
2642 message += ', use --username or --netrc to access it'
2644 raise ExtractorError(message, expected=True)
2645 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2646 raise ExtractorError(
2647 'Invalid parameters. Maybe URL is incorrect.',
2649 elif re.match(r'[^<]*Choose your language[^<]*', match):
2652 self.report_warning('Youtube gives an alert message: ' + match)
2654 playlist_title = self._html_search_regex(
2655 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2656 page, 'title', default=None)
2658 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2659 uploader = self._search_regex(
2660 r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
2661 page, 'uploader', default=None)
2663 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2666 uploader_id = mobj.group('uploader_id')
2667 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2669 uploader_id = uploader_url = None
2673 if not playlist_title:
2675 # Some playlist URLs don't actually serve a playlist (e.g.
2676 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2677 next(self._entries(page, playlist_id))
2678 except StopIteration:
2681 playlist = self.playlist_result(
2682 self._entries(page, playlist_id), playlist_id, playlist_title)
2684 'uploader': uploader,
2685 'uploader_id': uploader_id,
2686 'uploader_url': uploader_url,
2689 return has_videos, playlist
2691 def _check_download_just_video(self, url, playlist_id):
2692 # Check if it's a video-specific URL
2693 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2694 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2695 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
2696 'video id', default=None)
2698 if self._downloader.params.get('noplaylist'):
2699 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2700 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
2702 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2703 return video_id, None
2706 def _real_extract(self, url):
2707 # Extract playlist id
2708 mobj = re.match(self._VALID_URL, url)
2710 raise ExtractorError('Invalid URL: %s' % url)
2711 playlist_id = mobj.group(1) or mobj.group(2)
2713 video_id, video = self._check_download_just_video(url, playlist_id)
2717 if playlist_id.startswith(('RD', 'UL', 'PU')):
2718 # Mixes require a custom extraction process
2719 return self._extract_mix(playlist_id)
2721 has_videos, playlist = self._extract_playlist(playlist_id)
2722 if has_videos or not video_id:
2725 # Some playlist URLs don't actually serve a playlist (see
2726 # https://github.com/ytdl-org/youtube-dl/issues/10537).
2727 # Fallback to plain video extraction if there is a video id
2728 # along with playlist id.
2729 return self.url_result(video_id, 'Youtube', video_id=video_id)
2732 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
2733 IE_DESC = 'YouTube.com channels'
2734 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
2735 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
2736 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2737 IE_NAME = 'youtube:channel'
2739 'note': 'paginated channel',
2740 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2741 'playlist_mincount': 91,
2743 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2744 'title': 'Uploads from lex will',
2745 'uploader': 'lex will',
2746 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2749 'note': 'Age restricted channel',
2750 # from https://www.youtube.com/user/DeusExOfficial
2751 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2752 'playlist_mincount': 64,
2754 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2755 'title': 'Uploads from Deus Ex',
2756 'uploader': 'Deus Ex',
2757 'uploader_id': 'DeusExOfficial',
2760 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
2761 'only_matching': True,
2765 def suitable(cls, url):
2766 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2767 else super(YoutubeChannelIE, cls).suitable(url))
2769 def _build_template_url(self, url, channel_id):
2770 return self._TEMPLATE_URL % channel_id
2772 def _real_extract(self, url):
2773 channel_id = self._match_id(url)
2775 url = self._build_template_url(url, channel_id)
2777 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2778 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2779 # otherwise fallback on channel by page extraction
2780 channel_page = self._download_webpage(
2781 url + '?view=57', channel_id,
2782 'Downloading channel page', fatal=False)
2783 if channel_page is False:
2784 channel_playlist_id = False
2786 channel_playlist_id = self._html_search_meta(
2787 'channelId', channel_page, 'channel id', default=None)
2788 if not channel_playlist_id:
2789 channel_url = self._html_search_meta(
2790 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2791 channel_page, 'channel url', default=None)
2793 channel_playlist_id = self._search_regex(
2794 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2795 channel_url, 'channel id', default=None)
2796 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2797 playlist_id = 'UU' + channel_playlist_id[2:]
2798 return self.url_result(
2799 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
2801 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
2802 autogenerated = re.search(r'''(?x
)
2804 channel
-header
-autogenerated
-label|
2805 yt
-channel
-title
-autogenerated
2806 )[^
"]*"''', channel_page) is not None
2809 # The videos are contained in a single page
2810 # the ajax pages can't be used, they are empty
2813 video_id, 'Youtube', video_id=video_id,
2814 video_title=video_title)
2815 for video_id, video_title in self.extract_videos_from_page(channel_page)]
2816 return self.playlist_result(entries, channel_id)
2819 next(self._entries(channel_page, channel_id))
2820 except StopIteration:
2821 alert_message = self._html_search_regex(
2822 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2823 channel_page, 'alert', default=None, group='alert')
2825 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2827 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2830 class YoutubeUserIE(YoutubeChannelIE):
2831 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
2832 _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results|shared)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
2833 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
2834 IE_NAME = 'youtube:user'
2837 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2838 'playlist_mincount': 320,
2840 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2841 'title': 'Uploads from The Linux Foundation',
2842 'uploader': 'The Linux Foundation',
2843 'uploader_id': 'TheLinuxFoundation',
2846 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2847 # but not https://www.youtube.com/user/12minuteathlete/videos
2848 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2849 'playlist_mincount': 249,
2851 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2852 'title': 'Uploads from 12 Minute Athlete',
2853 'uploader': '12 Minute Athlete',
2854 'uploader_id': 'the12minuteathlete',
2857 'url': 'ytuser:phihag',
2858 'only_matching': True,
2860 'url': 'https://www.youtube.com/c/gametrailers',
2861 'only_matching': True,
2863 'url': 'https://www.youtube.com/gametrailers',
2864 'only_matching': True,
2866 # This channel is not available, geo restricted to JP
2867 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2868 'only_matching': True,
2872 def suitable(cls, url):
2873 # Don't return True if the url can be extracted with other youtube
2874 # extractor, the regex would is too permissive and it would match.
2875 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2876 if any(ie.suitable(url) for ie in other_yt_ies):
2879 return super(YoutubeUserIE, cls).suitable(url)
2881 def _build_template_url(self, url, channel_id):
2882 mobj = re.match(self._VALID_URL, url)
2883 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2886 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2887 IE_DESC = 'YouTube.com live streams'
2888 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2889 IE_NAME = 'youtube:live'
2892 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2894 'id': 'a48o2S1cPoo',
2896 'title': 'The Young Turks - Live Main Show',
2897 'uploader': 'The Young Turks',
2898 'uploader_id': 'TheYoungTurks',
2899 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2900 'upload_date': '20150715',
2901 'license': 'Standard YouTube License',
2902 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2903 'categories': ['News & Politics'],
2904 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2906 'dislike_count': int,
2909 'skip_download': True,
2912 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2913 'only_matching': True,
2915 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2916 'only_matching': True,
2918 'url': 'https://www.youtube.com/TheYoungTurks/live',
2919 'only_matching': True,
2922 def _real_extract(self, url):
2923 mobj = re.match(self._VALID_URL, url)
2924 channel_id = mobj.group('id')
2925 base_url = mobj.group('base_url')
2926 webpage = self._download_webpage(url, channel_id, fatal=False)
2928 page_type = self._og_search_property(
2929 'type', webpage, 'page type', default='')
2930 video_id = self._html_search_meta(
2931 'videoId', webpage, 'video id', default=None)
2932 if page_type.startswith('video') and video_id and re.match(
2933 r'^[0-9A-Za-z_-]{11}$', video_id):
2934 return self.url_result(video_id, YoutubeIE.ie_key())
2935 return self.url_result(base_url)
2938 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2939 IE_DESC = 'YouTube.com user/channel playlists'
2940 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2941 IE_NAME = 'youtube:playlists'
2944 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2945 'playlist_mincount': 4,
2947 'id': 'ThirstForScience',
2948 'title': 'ThirstForScience',
2951 # with "Load more" button
2952 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2953 'playlist_mincount': 70,
2956 'title': 'Игорь Клейнер',
2959 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2960 'playlist_mincount': 17,
2962 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2963 'title': 'Chem Player',
2969 class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
2970 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2973 class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
2974 IE_DESC = 'YouTube.com searches'
2975 # there doesn't appear to be a real limit, for example if you search for
2976 # 'python' you get more than 8.000.000 results
2977 _MAX_RESULTS = float('inf')
2978 IE_NAME = 'youtube:search'
2979 _SEARCH_KEY = 'ytsearch'
2980 _EXTRA_QUERY_ARGS = {}
2983 def _get_n_results(self, query, n):
2984 """Get a specified number of results for a query"""
2990 'search_query': query.encode('utf-8'),
2992 url_query.update(self._EXTRA_QUERY_ARGS)
2993 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2995 for pagenum in itertools.count(1):
2996 data = self._download_json(
2997 result_url, video_id='query "%s"' % query,
2998 note='Downloading page %s' % pagenum,
2999 errnote='Unable to download API page',
3000 query={'spf': 'navigate'})
3001 html_content = data[1]['body']['content']
3003 if 'class="search-message' in html_content:
3004 raise ExtractorError(
3005 '[youtube] No video results', expected=True)
3007 new_videos = list(self._process_page(html_content))
3008 videos += new_videos
3009 if not new_videos or len(videos) > limit:
3011 next_link = self._html_search_regex(
3012 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
3013 html_content, 'next link', default=None)
3014 if next_link is None:
3016 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
3020 return self.playlist_result(videos, query)
3023 class YoutubeSearchDateIE(YoutubeSearchIE):
3024 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
3025 _SEARCH_KEY = 'ytsearchdate'
3026 IE_DESC = 'YouTube.com searches, newest videos first'
3027 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
3030 class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
3031 IE_DESC = 'YouTube.com search URLs'
3032 IE_NAME = 'youtube:search_url'
3033 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
3035 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
3036 'playlist_mincount': 5,
3038 'title': 'youtube-dl test video',
3041 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
3042 'only_matching': True,
3045 def _real_extract(self, url):
3046 mobj = re.match(self._VALID_URL, url)
3047 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
3048 webpage = self._download_webpage(url, query)
3049 return self.playlist_result(self._process_page(webpage), playlist_title=query)
3052 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
3053 IE_DESC = 'YouTube.com (multi-season) shows'
3054 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
3055 IE_NAME = 'youtube:show'
3057 'url': 'https://www.youtube.com/show/airdisasters',
3058 'playlist_mincount': 5,
3060 'id': 'airdisasters',
3061 'title': 'Air Disasters',
3065 def _real_extract(self, url):
3066 playlist_id = self._match_id(url)
3067 return super(YoutubeShowIE, self)._real_extract(
3068 'https://www.youtube.com/show/%s/playlists' % playlist_id)
3071 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
3073 Base class for feed extractors
3074 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
3076 _LOGIN_REQUIRED = True
3080 return 'youtube:%s' % self._FEED_NAME
3082 def _real_initialize(self):
3085 def _entries(self, page):
3086 # The extraction process is the same as for playlists, but the regex
3087 # for the video ids doesn't contain an index
3089 more_widget_html = content_html = page
3090 for page_num in itertools.count(1):
3091 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
3093 # 'recommended' feed has infinite 'load more' and each new portion spins
3094 # the same videos in (sometimes) slightly different order, so we'll check
3095 # for unicity and break when portion has no new videos
3096 new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
3102 for entry in self._ids_to_results(new_ids):
3105 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
3109 more = self._download_json(
3110 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
3111 'Downloading page #%s' % page_num,
3112 transform_source=uppercase_escape)
3113 content_html = more['content_html']
3114 more_widget_html = more['load_more_widget_html']
3116 def _real_extract(self, url):
3117 page = self._download_webpage(
3118 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
3119 self._PLAYLIST_TITLE)
3120 return self.playlist_result(
3121 self._entries(page), playlist_title=self._PLAYLIST_TITLE)
3124 class YoutubeWatchLaterIE(YoutubePlaylistIE):
3125 IE_NAME = 'youtube:watchlater'
3126 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3127 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
3130 'url': 'https://www.youtube.com/playlist?list=WL',
3131 'only_matching': True,
3133 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
3134 'only_matching': True,
3137 def _real_extract(self, url):
3138 _, video = self._check_download_just_video(url, 'WL')
3141 _, playlist = self._extract_playlist('WL')
3145 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
3146 IE_NAME = 'youtube:favorites'
3147 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
3148 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
3149 _LOGIN_REQUIRED = True
3151 def _real_extract(self, url):
3152 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
3153 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
3154 return self.url_result(playlist_id, 'YoutubePlaylist')
3157 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
3158 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3159 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
3160 _FEED_NAME = 'recommended'
3161 _PLAYLIST_TITLE = 'Youtube Recommended videos'
3164 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
3165 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
3166 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
3167 _FEED_NAME = 'subscriptions'
3168 _PLAYLIST_TITLE = 'Youtube Subscriptions'
3171 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
3172 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
3173 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
3174 _FEED_NAME = 'history'
3175 _PLAYLIST_TITLE = 'Youtube History'
3178 class YoutubeTruncatedURLIE(InfoExtractor):
3179 IE_NAME = 'youtube:truncated_url'
3180 IE_DESC = False # Do not list
3181 _VALID_URL = r'''(?x
)
3183 (?
:\w
+\
.)?
[yY
][oO
][uU
][tT
][uU
][bB
][eE
](?
:-nocookie
)?\
.com
/
3186 annotation_id
=annotation_
[^
&]+|
3192 attribution_link
\?a
=[^
&]+
3198 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
3199 'only_matching': True,
3201 'url': 'https://www.youtube.com/watch?',
3202 'only_matching': True,
3204 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
3205 'only_matching': True,
3207 'url': 'https://www.youtube.com/watch?feature=foo',
3208 'only_matching': True,
3210 'url': 'https://www.youtube.com/watch?hl=en-GB',
3211 'only_matching': True,
3213 'url': 'https://www.youtube.com/watch?t=2372',
3214 'only_matching': True,
3217 def _real_extract(self, url):
3218 raise ExtractorError(
3219 'Did you forget to quote the URL? Remember that & is a meta '
3220 'character in most shells, so you want to put the URL in quotes, '
3222 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3223 ' or simply youtube-dl BaW_jenozKc .',
3227 class YoutubeTruncatedIDIE(InfoExtractor):
3228 IE_NAME = 'youtube:truncated_id'
3229 IE_DESC = False # Do not list
3230 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
3233 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3234 'only_matching': True,
3237 def _real_extract(self, url):
3238 video_id = self._match_id(url)
3239 raise ExtractorError(
3240 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),